Research Scientist @GoogleDeepMind. Gemini multimodal pretraining, Vision Banana, Genie2, Gemini Robotics 1.5
Joined August 2022
- Tweets45
- Following241
- Followers695
- Likes338
Pinned Tweet
🚀 Excited to announce Vision Banana 🍌 and our new paper: “Image Generators are Generalist Vision Learners”. We turn Nano Banana Pro into a state-of-the-art visual generation and understanding model.
🖼️ Check out our gallery at vision-banana.github.io
🧵 (1/N) continue ⬇️
We are accelerating... recursively!
I did say we'd be releasing our models periodically...introducing Gemini 4 Carbon, our next frontier model.
Following Argon's release just two weeks ago, Carbon shows the pace at which we’re pushing the frontier, it ranks #1 on the recently updated v5.0 of @ArtificialAnlys Intelligence Index at 59. It also leads across key cybersecurity evaluations scoring 88.2% on SEC-bench Pro for finding vulnerabilities, 54.8% on ExploitGym for exploitation, and 71.0% on CWE-bench for patching.
We’re seeing significant improvements in long-horizon tasks even compared to Argon, and we’ve strengthened frontier safeguards.
As we did with Argon, we’re going to roll it out gradually + responsibly. Some trusted cyber defenders will get access starting this week. We'll be expanding it to more partners through our Fairwind Program, ahead of wider availability soon, so hang tight!
Welcome!
OpenAI models are coming to Google Cloud.
We're bringing our frontier models and Codex agentic workflows to Google Cloud's Model Garden, so enterprises can use our technology where they already build.
openai.com/index/openai-mode…
Shangbang Long retweeted
Enjoy our latest model update, Nano Banana 2.1! It improves things tool use and instruction following (especially multi-turn), giving you more reliable and useful generations and edits.
Our team (Gemini Vision) is hiring in Mountain View / Zurich / New York / LA:
google.com/about/careers/app…
Shangbang Long retweeted
Lots of discussion out there about our next model(!), so I wanted to give an early look as soon as possible. Introducing Gemini 4 Argon!
It shows frontier performance in complex workflows, cyber defense and software engineering. Teams are using it extensively at Google, from coding to quantum computing, great feedback.
Here’s a look at the benchmarks:
I've been using 3.8 Flash internally and it is much much more intelligent than previous ones. Proud of what our team has delivered!
Today we’re introducing a new 3.8 Flash model, our 3rd Flash release in just 6 wks.
It delivers significant leaps from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. On DeepSWE v1.1, it outperforms most larger frontier models in autonomously solving complex engineering problems end to end, at a fraction of the cost.
More details here: blog.google/innovation-and-a…
Shangbang Long retweeted
1/2 Introducing Nano Banana 2 Lite! We are working hard at the next frontier model, but in the meantime enjoy this fast and cheap Nano Banana (Pico Banana?). It returns images in only a few seconds, and with most of the smarts of the NB2 model! deepmind.google/models/gemin…
Our team is hiring: google.com/about/careers/app…
Our Gemini Vision team @GoogleDeepMind is hiring in MTV/SF.
Join us to push the frontiers of visual perception, reasoning and generation, and contribute to Gemini, Nano Banana and Omni. Also get to do cool research such as Vision Banana 🍌: deepmind.google/research/pub….
Job posting below.
It's one of the best times to be working on Vision as the frontier is moving rapidly, come join us!
Our research was hugely inspired by the previous work that shows zero-shot understanding and reasoning capabilities in video generators like Veo 3.
Video models might be even better vision (and action) learners 🧐.
Shangbang Long retweeted
Vision Banana 🍌 is here in Rio at @iclr_conf. I'll be at the Google Booth tomorrow at 10 AM doing a Demo at the @GoogleDeepMind Kiosk for folks to try out the model. I have some cool demos but I wanna do BYOImages. Looking forward to seeing folks!
Shangbang Long retweeted
vision🍌 is here vision-banana.github.io/
if you got into computer vision the way I did, starting with pixel-level labeling tasks like segmentation, edges, depth, or surface normals, you’ll probably feel the same seeing these results -- something big has quietly shifted, and it’s going to change how we approach these problems for good 🧵
Shangbang Long retweeted
Are we finally witnessing the GPT-3 moment for computer vision? We just dropped Vision Banana 🍌 , a vision foundation model that seamlessly unifies generation and perception by treating all vision tasks as just another image generation problem.
1/N
#googledeepmind #nanobanana
🧵 (8/N) The Vision Banana works is greatly inspired and guided by our leads: @oliver_wang2 , @sainingxie , @howardzzh , Kaiming, Tom, @jalayrac , and @RSoricut .
🧵 (N/N) Remember to check our demo by @NithishKannen at ICLR! It’s located right at Google’s Booth.
research.google/conferences-…
